• Corpus ID: 249209761

CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference

@inproceedings{Nygaard2022CONNECTAN,
  title={CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference},
  author={Andreas Nygaard and Emil Brinch Holm and Steen Hannestad and Thomas Tram},
  year={2022}
}
Bayesian parameter inference is an essential tool in modern cosmology, and typically requires the calculation of 105–106 theoretical models for each inference of model parameters for a given dataset combination. Computing these models by solving the linearised Einstein-Boltzmann system usually takes tens of CPU core-seconds per model, making the entire process very computationally expensive. In this paper we present connect, a neural network framework emulating class computations as an easy-to… 
2 Citations

CosmicNet II: emulating extended cosmologies with efficient and accurate neural networks

A more efficient set of networks that are already trained for extended cosmologies beyond ΛCDM, with massive neutrinos, extra relativistic degrees of freedom, spatial curvature, and dynamical dark energy are presented.

Fast and robust Bayesian Inference using Gaussian Processes with GPry

The GPry algorithm for fast Bayesian inference of general (non-Gaussian) posteriors with a moderate number of parameters is presented, based on generating a Gaussian Process surrogate model of the log-posterior aided by a Support Vector Machine classifier that excludes extreme or non-flnite values.

References

SHOWING 1-10 OF 30 REFERENCES

CosmicNet. Part I. Physics-driven implementation of neural networks within Einstein-Boltzmann Solvers

A new concept for speeding up cosmological codes with neural networks by not substituting the whole EBS by a machine learning algorithm, but only its most problematic and least parallelizable step: the integration of perturbation equations over time.

Accelerating cosmological inference with Gaussian processes and neural networks -- an application to LSST Y1 weak lensing and galaxy clustering

This paper presents a method to accelerate cosmological inference using emulators based on Gaussian process regression and neural networks, and shows that it leads to high-fidelity posterior contours, with an order of magnitude speed-up.

Fast cosmological parameter estimation using neural networks

It is found that the average error in the power spectra is typically 2 − 3% of cosmic variance, and that COSMONET is ∼ 7 × 10 4 faster than CAMB (for flat models) and ∼ 6 × 10 6 times faster than the official WMAP3 likelihood code.

cosmonet: fast cosmological parameter estimation in non-flat models using neural networks

We present a further development of a method for accelerating the calculation of cosmic microwave background (CMB) power spectra, matter power spectra and likelihood functions for use in cosmological

Euclid-era cosmology for everyone: Neural net assisted MCMC sampling for the joint 3x2 likelihood

A fully non-invasive use of machine learning in order to enable open research on Euclid-sized data sets and publicly provides the neural nets which memorise and output all 3x2 power spectra at a EuclID-like sky coverage and redshift binning.

Bayesian emulator optimisation for cosmology: application to the Lyman-alpha forest

This is the first demonstration of Bayesian optimisation applied to large-scale structure emulation, and it is anticipated the technique will generalise to many other probes such as galaxy clustering, weak lensing and 21cm.

Accelerating Large-Scale-Structure data analyses by emulating Boltzmann solvers and Lagrangian Perturbation Theory

The linear matter power spectrum is an essential ingredient in all theoretical models for interpreting large-scale-structure observables. Although Boltzmann codes such as CLASS or CAMB are very

COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys

We present CosmoPower, a suite of neural cosmological power spectrum emulators providing orders-of-magnitude acceleration for parameter estimation from two-point statistics analyses of Large-Scale

SPECULATOR: Emulating Stellar Population Synthesis for Fast and Accurate Galaxy Spectra and Photometry

A fast, accurate, and flexible framework for emulating stellar population synthesis (SPS) models for predicting galaxy spectra and photometry, with a massive reduction in the computational resources required to infer the physical properties of galaxies from observed spectra or photometry and simulate galaxy populations under SPS models.

Conservative Constraints on Early Cosmology: an illustration of the Monte Python cosmological parameter inference code

Models for the latest stages of the cosmological evolution rely on a less solid theoretical and observational ground than the description of earlier stages like BBN and recombination. As suggested in